© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2825
    Prev
    Next
    INDEX
    Explanations

    define function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¹¶æł¹æį®
    -0.08
     bowiem
    -0.07
    并åIJĮæŶ
    -0.07
    åįģåĪĨéĩįè§Ĩ
    -0.07
    形象åĴĮ
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    å¹¶è¿Ľè¡Į
    -0.06
    并æİ¥åıĹ
    -0.06
     tỼ
    -0.06
    æĪijåľ¨è¿ĻéĩĮ
    -0.06
    POSITIVE LOGITS
     alike
    0.08
    uracy
    0.07
    sert
    0.07
     thereof
    0.07
    fadeOut
    0.07
     sowie
    0.07
     dermed
    0.07
    èĩ³å°ijæľī
    0.07
    é¦ĸ
    0.07
     afterward
    0.07
    Activations Density 0.025%

    No Known Activations